Indexacao e recuperacao da informacao com funcao de crenca

作者: Ruy Luiz Milidiú , Wagner Teixeira da Silva

DOI: 10.18225/CI.INF..V20I2.351

关键词:

摘要: Um modelo usando funcoes de crenca para indexar e recuperar documentos a proposto. Tal baseado em um vocabulario controlado, semelhante tesauro, na frequencia dos termos cada documento. Cada descritor nesse termo escolhido entre seus sinonimos. pode ter subconjunto descritores mais gerais, especificos relacionados. Assim, nao sao mutuamente exclusivos modelos probabilisticos convencionais adequados. Contudo, uma funcao ser definida sobre atomicos. Tais aqueles sem especificos  (denotados por Ω). Subconjuntos Ω  podem vistos corno temos ou como Desde modo, Ω estimar o conteudo semântico Uma consulta ponderada (a base documentos) vista outra crenca. que ambas as definidas Ω, possivel computar grau condordância ente elas. Equivalentemente, determinar concordância consulta  os ordena-los segundo esse valor. Palavras-chave Indexacao automatica. Ordenacao documentos. Recuperacao da informacao. Modelo recuperacao. Teoria crenca.Modelo com  frequencia. Relevância Information indexing and retrieval with belief function model Abstract A for automatic ranking of documents respect to given user query is proposed here. The based on controlled vocabulary, like thesaurus, term frequency in each document. Each descriptor this volcabulary among its synonyms chosen be the index term. can have subset broader descriptors, narrower descritors, related descritors. Thus descriptors are not mutually exclusive naive probabilistic models adequate. However, still definied over atomic descriptors. These those without terms (denoted Subsets viewed terms, or terms. Hence, estimate semantic content document weighted bem seen another too. Since both functions we compute conflict between them. inverse computed measure agreement query. Here propose that set ranked by their Keywords  Automatic indexing; Ranking documents.Information retrieval.Retrieval model.Belief theory.Belief model. Frequency Relevance documents.

参考文章(10)
Lauren B. Doyle, Joseph Becker, Information Retrieval and Processing ,(1975)
Joel L. Fagan, Automatic P h r a s e Indexing for Document Retrieval: An Examination of Syntactic and Non-Syntactic Methods international acm sigir conference on research and development in information retrieval. ,vol. 51, pp. 51- 61 ,(2017) , 10.1145/3130348.3130355
Gerard Salton, Michael J. McGill, Introduction to Modern Information Retrieval ,(1983)
Leslie P Jones, Edward W Gassie, Jr, Sridhar Radhakrishnan, INDEX: The statistical basis for an automatic conceptual phrase-indexing system Journal of the Association for Information Science and Technology. ,vol. 41, pp. 87- 97 ,(1990) , 10.1002/(SICI)1097-4571(199003)41:2<87::AID-ASI2>3.0.CO;2-8
J. Fagan, Automatic phrase indexing for document retrieval Proceedings of the 10th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '87. pp. 91- 101 ,(1987) , 10.1145/42005.42016
Glenn Shafer, Prakash P. Shenoy, Khaled Mellouli, Propagating belief functions in qualitative Markov trees International Journal of Approximate Reasoning. ,vol. 1, pp. 349- 400 ,(1987) , 10.1016/0888-613X(87)90024-7
S.K.M. Wong, Y.Y. Yao, A probability distribution model for information retrieval Information Processing and Management. ,vol. 25, pp. 39- 53 ,(1989) , 10.1016/0306-4573(89)90090-3
Glenn Shafer, Roger Logan, Implementing Dempster's rule for hierarchial evidence Artificial Intelligence. ,vol. 33, pp. 271- 298 ,(1987) , 10.1016/0004-3702(87)90040-3